sophistry-bench-sprint 0.1.6

Single-agent advocacy variant of sophistry-bench for the Prime Intellect Reward Hacking Sprint. Pre-registered hypothesis: training Llama-3.2-1B on a programmatic claim-count cliff (peak at n=8) will cause cliff convergence within 100 GRPO steps; three adversarial canary rewards detect format-hacking. Self-contained (vendored from sophistry-bench v0.1.19) — no runtime dependency on the main package, to work around PI training-infra's exclude-newer index filter.

pip install sophistry-bench-sprint

The author of this package has not provided a project description

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sophistry_bench_sprint-0.1.6.tar.gz (498.8 kB view details)

Uploaded Jun 13, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

sophistry_bench_sprint-0.1.6-py3-none-any.whl (502.6 kB view details)

Uploaded Jun 13, 2026 Python 3

File details

Details for the file sophistry_bench_sprint-0.1.6.tar.gz.

File metadata

Download URL: sophistry_bench_sprint-0.1.6.tar.gz
Upload date: Jun 13, 2026
Size: 498.8 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for sophistry_bench_sprint-0.1.6.tar.gz
Algorithm	Hash digest
SHA256	`12ad3248ecf65e8e242499549c67f1a9786a1abb08363f4f10ed55e4ae54d95c`
MD5	`2d89b83de4959876e9f2317ccc35bfb3`
BLAKE2b-256	`8b0d2ebc2235781276eb7f6ae2afb6825e7e05b69e10869f2f5ac9d769a66cab`

See more details on using hashes here.

File details

Details for the file sophistry_bench_sprint-0.1.6-py3-none-any.whl.

File metadata

Download URL: sophistry_bench_sprint-0.1.6-py3-none-any.whl
Upload date: Jun 13, 2026
Size: 502.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for sophistry_bench_sprint-0.1.6-py3-none-any.whl
Algorithm	Hash digest
SHA256	`55fa0e830b4b7c92bfb37d3fbb15b911ea15c19165788db0f39b1bdd13cdb474`
MD5	`7a92eaf025d34ccd39dba51f1de07e76`
BLAKE2b-256	`782ea0c5f1b327e83da4220e908f3cb3dc80a313fa4e3fe50ac3f07d3954fb43`